R Notebook

dataset <- read.csv("Household_Travel_Survey_Trips.csv") 
head(dataset)

 snohomish_trips <- dataset[dataset$sample_county == "Snohomish" & dataset$survey_year == 2019,]

snohomish_trips

# calculate the number of trips per person
total_trips <- tapply(snohomish_trips$trip_id, snohomish_trips$person_dim_id, sum)

# average distance per trip (for the latter use trip_path_distance).
average_distance <- tapply(snohomish_trips$trip_path_distance, snohomish_trips$person_dim_id, mean)

 trips_per_person <- aggregate(trip_path_distance ~ trip_id, data = snohomish_trips, FUN = length)

colnames(trips_per_person) <- c("trip_id", "num_trips")

avg_distance_per_trip <- aggregate(trip_path_distance ~ trip_id, data = snohomish_trips, FUN = mean)

colnames(avg_distance_per_trip) <- c("trip_id", "avg_distance")

results <- merge(trips_per_person, avg_distance_per_trip, by = "trip_id")

results

person_dataset <- dataset[, c("trip_id", "age", "gender", "employment", "rent_own")]

person_results <- merge(results, person_dataset, by = "trip_id")

person_results

library(ggplot2)

# Trip Number
ggplot(person_results, aes(x = age, y = num_trips)) + 
  geom_boxplot(aes(fill = age)) +
  labs(title = "Trip Number by Age", x = "Age", y = "Trip Number")

# Trip Number by Rent/Ownership Status
ggplot(person_results, aes(x = rent_own, y = num_trips)) + 
  geom_boxplot(aes(fill = rent_own)) +
  labs(title = "Trip Number by Rent/Ownership Status", x = "Rent/Ownership Status", y = "Trip Number")

# Trip Distance by Rent/Ownership Status
ggplot(person_results, aes(x = rent_own, y = avg_distance)) + 
  geom_boxplot(aes(fill = rent_own)) +
  labs(title = "Trip Distance by Rent/Ownership Status", x = "Rent/Ownership Status", y = "Trip Distance")

# Trip Distance by Gender
ggplot(person_results, aes(x = gender, y = avg_distance)) + 
  geom_boxplot(aes(fill = gender)) +
  labs(title = "Trip Distance by Gender", x = "Gender", y = "Trip Distance")